CN113811832B

CN113811832B - Real-time optimization of autonomous vehicle routes

Info

Publication number: CN113811832B
Application number: CN202080034926.6A
Authority: CN
Inventors: M.库比
Original assignee: Wing Aviation LLC
Current assignee: Wing Aviation LLC
Priority date: 2019-05-10
Filing date: 2020-04-15
Publication date: 2024-03-15
Anticipated expiration: 2040-04-15
Also published as: CN113811832A; WO2020231591A1; AU2020275699B2; AU2020275699A1; US20200356115A1; US11099583B2; EP3938857A1; EP3938857A4

Abstract

Techniques are provided to improve routing of autonomous vehicles through highly congested areas. In some embodiments, the route comprising the sequence of timing space reservations is provided to the autonomous vehicle by the route reservation system. In some embodiments, the route reservation system detects route change status (including but not limited to the arrival of autonomous vehicles at the waiting area), determines a new route for autonomous vehicles passing through the highly congested area, and sends the new route to the autonomous vehicles for navigation from the waiting area to the destination.

Description

Real-time optimization of autonomous vehicle routes

Cross Reference to Related Applications

The present application claims the benefit of U.S. application Ser. No. 16/409,563, filed 5/10 in 2019, which is incorporated herein by reference in its entirety.

Technical Field

The application relates to real-time optimization of autonomous vehicle routes.

Background

Autonomous vehicles, including but not limited to aircraft such as Unmanned Aerial Vehicles (UAVs), are increasingly being used for a variety of tasks. For example, autonomous vehicles are commonly used to perform logistics-related tasks such as delivering packages from a centralized warehouse to various destinations, or rearranging inventory items in a warehouse.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

In some embodiments, a non-transitory computer-readable medium is provided. The computer-readable medium has stored thereon computer-executable instructions that, in response to execution by one or more processors of one or more computing devices, cause the computing devices to perform actions for updating a reserved route of an autonomous vehicle. The actions include planning a new route to replace the reserved route; transmitting the new route to the autonomous vehicle; and responsive to receiving an acknowledgement from the autonomous vehicle that the new route is accepted, deleting one or more timing space reservations associated with the reserved route.

In some embodiments, an autonomous vehicle is provided. The autonomous vehicle includes: a communication interface, one or more propulsion devices, one or more processors, and a computer-readable medium. The computer-readable medium has stored thereon computer-executable instructions that, in response to execution by the one or more processors, cause an autonomous vehicle to perform actions comprising: operating the propulsion device to traverse (reverse) the reserved route; and when traversing the reserved route: receiving the updated route via the communication interface; analyzing the updated route to determine whether the updated route is acceptable; and in response to determining that the updated route is acceptable: transmitting an acknowledgement of the updated route via the communication interface; and operating the propulsion device to traverse the updated route instead of the reserved route by the autonomous vehicle.

Drawings

The foregoing aspects and many of the attendant advantages of this invention will become more readily appreciated as the same become better understood by reference to the following detailed description, when taken in conjunction with the accompanying drawings, wherein:

1A-1B illustrate a non-limiting example embodiment of an autonomous vehicle navigating a route allocated by a centralized controller, in accordance with aspects of the present disclosure;

FIG. 2 illustrates an example embodiment in which vehicles are expected to travel through high traffic flow bottlenecks;

FIG. 3 is a block diagram illustrating components associated with non-limiting example embodiments of route reservation systems and non-limiting example embodiments of autonomous vehicles, according to aspects of the present disclosure;

4A-4B are flow diagrams illustrating non-limiting example embodiments of a method of optimizing a route of an autonomous vehicle according to aspects of the present disclosure;

5A-5C illustrate example embodiments of routes with detour and detour removal according to various aspects of the present disclosure;

fig. 6 illustrates an example of how a new sequence of timing space reservations conflicts with existing timing space reservations in accordance with aspects of the present disclosure; and

fig. 7A-7B are flow diagrams illustrating non-limiting example embodiments of methods for autonomous vehicle navigation optimized routes according to various aspects of the present disclosure.

Detailed Description

Autonomous vehicles, including but not limited to aircraft such as Unmanned Aerial Vehicles (UAVs), are increasingly being used for a variety of tasks. For example, autonomous vehicles are commonly used to perform logistics-related tasks such as delivering packages from a centralized warehouse to various destinations, or rearranging inventory items in a warehouse. Because the availability of reliable high bandwidth communication between the autonomous vehicle and the centralized controller cannot be assumed (particularly when operating outside the line of sight of the centralized controller), routes and other tasks may be sent from the centralized controller to the autonomous vehicle before the autonomous vehicle starts, and the autonomous vehicle may then autonomously navigate the assigned routes.

While autonomous vehicles use various onboard sensors for navigation, the vehicles (particularly aircraft) may not include sensors or peer-to-peer communication that would allow the vehicles to avoid each other while navigating. To increase safety, the centralized controller may route autonomous vehicles such that no two vehicles are expected to be within a predetermined safety radius of each other at any point in time.

Fig. 1A-1B illustrate non-limiting example embodiments of autonomous vehicle navigation routes distributed by a centralized controller, according to aspects of the present disclosure. As shown, the route includes a sequence of timing space reservations 106, 108, 110, 112. Each timing space reservation is a reservation tracked by a centralized controller of an area (two-dimensional) or volume (three-dimensional) over a given period of time that the vehicle 102 is expected to traverse the area or volume. The centralized controller stores timing space reservations for planning routes to be allocated to the carriers, and the centralized controller ensures that no two carriers are expected to be within the same space at the same time based on the timing space reservations. The timing space reservation is sized to accommodate both the carrier 102 and a safety margin (margin) 104 around the carrier 102. The carrier 102 may not be aware of the reservation and may only be provided with a path to navigate autonomously through the reserved space.

As shown in fig. 1A, the current time is 13:15:27, and carrier 102 is within first time interval reservation 106. When navigating the path, the carrier 102 will next enter the space associated with the second timing space reservation 108. The second timing space reservation 108 is reserved from 13:15:00 to 13:17:15, and carriers 102 are expected to pass through the space associated with the second timing space reservation 108 during that time. Carrier 102 will then go through the space associated with third timing space reservation 110 reserved from 13:16:30 to 13:19:30, and then go through the space associated with fourth timing space reservation 112 reserved from 13:18:15 to 13:21:45. It will be noted that as the sequence proceeds, the time period reserved for each timing space will increase. This is done to accommodate the uncertainty accumulated in the elapsed time of each timing space reservation. The illustrated time periods for which the timing space reservations are reserved are non-limiting examples, and in various embodiments the amount of time reserved in each timing space reservation and the amount of increase in the time period over the sequence of timing space reservations may be different than those illustrated.

In some embodiments, the entire sequence of timing space reservations may be maintained by the centralized controller until the vehicle 102 has completed the entire route. However, maintaining a reservation for the entire path may be too restrictive, as it may be assumed that after the end time of the timing space reservation has expired, the carrier 102 is no longer within the associated space and thus the associated space may be reused for another route. Fig. 1B illustrates a cleanup (clearup) performed by the centralized controller as the vehicle 102 navigates the route. In FIG. 1B, the current time is 13:18:21, and the centralized controller assumes that carrier 102 is within the space associated with third timing space reservation 110. Thus, the centralized controller has deleted the first timing space reservation 106 and the second timing space reservation 108, neither of which represent space that is expected to occur in the future for the vehicle 102. The combination of future timing space reservations, such as fourth timing space reservation 112, and the deletion of past timing space reservations 106, 108 allows carrier 102 to traverse the space for which a collision is expected to be cleared, while maximizing the use of space that has been traversed.

While these techniques may effectively resolve autonomous vehicle travel conflicts, problems can occur in situations where vehicles are expected to travel through common paths or other high traffic flow bottlenecks. Fig. 2 shows an example embodiment in which the vehicle is expected to travel through a high traffic flow bottleneck. As shown, the carriers leave the warehouse 202, travel through the route, and then pause in a waiting area 204 near the warehouse 202. The first vehicle may travel along route one to access the first location and the second location before returning to the waiting area 204, and the second vehicle may travel along route two to access the third location, the fourth location, and the fifth location before returning to the waiting area 204.

Warehouse 202 may have a limited area through which vehicles must travel upon return, such as an opening in a wall for an aircraft, or a garage entrance for a wheeled vehicle, so the returning vehicle will wait in waiting area 204 until the area intended for return to warehouse 202 is cleared. When combining multiple vehicles traversing a route provided by a centralized controller as described above, it is clear that the path from waiting area 204 to warehouse 202 is a significant bottleneck. The centralized controller is configured to provide each vehicle with the following routes: the route is expected to be clear from the start point to the end point while the vehicle is navigating the route. However, for each timing space reservation in the route, the uncertainty of the vehicle position increases. Thus, the reservation of the timing space from waiting area 204 to warehouse 202 will last for a significant amount of time.

As a non-limiting example, if the first timing space reservation is one minute long (i.e., the vehicle is expected to pass the space associated with the first timing space reservation in one minute or less) and each timing space reservation in the sequence is thirty seconds longer than the previous timing space reservation to accommodate the accumulated positional uncertainty, then a route that includes only ten timing space reservations will have a final timing space reservation that lasts five minutes and thirty seconds. If the route has an end point within warehouse 202, this means that the path from waiting area 204 to warehouse 202 will be blocked for five minutes and thirty seconds even if the vehicle would be expected to traverse the path from waiting area 204 to warehouse 202 in a minute or less. This severely limits the number of carriers that the system can accommodate.

This problem is particularly important for aircraft. While aircraft may land in waiting area 204 near warehouse 202 while waiting for an opportunity for a path to warehouse 202 to clear, the limited space in the drop area (particularly when accommodating safety margins around each aircraft) limits the number of aircraft that may be accommodated. It may be desirable for the aircraft to hover rather than land in the waiting area 204 so that the aircraft may be stacked vertically as well as horizontally to accommodate more aircraft in the waiting area 204. However, the hovering aircraft will consume battery power, and thus may not be able to hover in the waiting area 204 for a significant amount of time without significantly limiting the range that the vehicle can cover on the path. What is desired is a technique for managing timing space reservations that helps reduce the amount of time a vehicle must wait in a waiting area before traveling through a high traffic flow bottleneck.

In some embodiments of the present disclosure, a route reservation system is enhanced (augmented) to automatically optimize and adjust the route of an autonomous vehicle in real time. In some embodiments, the route reservation system generates a route comprising a sequence of timing space reservations prior to navigating the route by the autonomous vehicle. The timing space reservation is used to exclude other autonomous vehicles from the associated space during the indicated time period. In the event that no further indication is received, these routes serve as a baseline for the autonomous vehicle to follow, and should allow the aircraft to safely travel through the route under the control of the route reservation system without collision with another autonomous vehicle. When the autonomous vehicle reaches a defined area (such as the end of warehouse 202) near the high traffic flow bottleneck area, the final route may be determined by the route reservation system and sent to the autonomous vehicle to replace the baseline route. Due to the lack of accumulated uncertainty errors, the final route may include tighter reserved margins, thereby allowing more autonomous vehicles to traverse high traffic flow bottlenecks.

Fig. 3 is a block diagram illustrating components associated with non-limiting example embodiments of route reservation systems and non-limiting example embodiments of autonomous vehicles, according to various aspects of the present disclosure.

Route reservation system 302 is configured to generate a route for safe travel by an autonomous vehicle and to transmit the route to the autonomous vehicle. In some embodiments, route reservation system 302 includes one or more computing devices, such as a desktop computing device, a laptop computing device, a rack-mounted server computing device, a tablet computing device, a mobile computing device, or other computing device configured to provide the following components. In some embodiments, route reservation system 302 includes one or more computing devices of a cloud computing system configured to provide the following components.

As shown, route reservation system 302 includes a communication interface 308, a route determination engine 306, a change detection engine 310, and a reservation data store 312.

In some embodiments, route determination engine 306 is configured to plan a non-conflicting route for transmission to an autonomous vehicle. The route determination engine 306 uses the start position, the end point, and one or more waypoints to determine a path to travel and then determines a sequence of timing space reservations along the path that do not overlap with any other timing space reservations in order to ensure that the path can be safely traveled.

In some embodiments, change detection engine 310 is configured to detect a condition indicating that a new route should be calculated and sent to the autonomous vehicle. As discussed in further detail below, conditions may include, but are not limited to, arrival wait area 204, a fault condition of an autonomous vehicle, and removal of an obstacle or conflicting timing space reservation.

Generally, the word "engine" as used herein refers to logic embodied in hardware and/or software instructions that may be written in a programming language, such as C, C ++, C#, COBOL, JAVA ^TM 、PHP、Perl、HTML、CSS、JavaScript、VBScript、ASPX、Microsoft.NET ^TM Go, etc. The engine may be compiled into an executable program or written in an interpreted programming language. The engine may be invoked from other engines or the engine itself. Generally, the engines described herein refer to logical components that may be combined with other engines or may be divided into sub-engines. The engine may be stored in any type of computer-readable medium or computer storage device and may be stored on and executed by one or more general-purpose computers, creating a special-purpose computer configured to provide the engine.

The communication interface 308 includes hardware and software to enable any suitable communication technology for communicating with the autonomous vehicle. In some embodiments, communication interface 308 of route reservation system 302 may be a wired interface, such as Ethernet, USB, fireWire (FireWire), or other wired communication technology that allows route reservation system 302 to access a local area network. The local area network to which the communication interface 308 is communicatively coupled may include one or more Wi-Fi access points (or other wireless access points) that allow other devices to communicate with the route reservation system 302 via wireless communication techniques. The local area network may also be coupled to a wide area network, such as the internet. The communication interface 308 will typically be a wired communication interface 308 due to the nature of the route reservation system 302, but the present embodiment should not be considered limiting. In some embodiments, the communication interface 308 may be a wireless communication interface 308, the wireless communication interface 308 configured to provide wireless communication using technologies including, but not limited to, wi-Fi, wiMAX, 2G, 3G, 4G, 5G, LTE, or bluetooth.

Reservation data storage 312 is configured to store a sequence of timing space reservations associated with a route to be traversed by an autonomous vehicle. Route reservation system 302 may access reservation data store 312 to determine whether a desired headroom reservation is available and may store the new headroom reservation when it is determined that the new headroom reservation does not conflict with an existing headroom reservation. As described above, once the end of the reserved time period has elapsed, route reservation system 302 may delete the timing space reservation from reservation data storage 312.

As will be appreciated by one of ordinary skill in the art, the "data store" described herein may be any suitable device configured to store data for access by a computing device. One example of a data store is a key value store. However, any other suitable storage technology and/or device capable of organizing and storing data may be used, such as a relational database management system (RDBMS), an object database, and the like. Other examples of data storage devices may also include data stored on computer-readable storage media in an organized manner.

One example of a data storage device that includes reliable storage and is low overhead is a file system or database management system that stores data in files (or records) on a computer readable medium such as flash memory, random Access Memory (RAM), hard disk drive, and the like. Such data storage may be used locally by autonomous vehicles 304. One example of a data store is a highly reliable high-speed RDBMS or key-value store executing on one or more computing devices and accessible over a high-speed packet-switched network. Such data storage may be used by components of route reservation system 302. Those of ordinary skill in the art will recognize that the separate data stores described herein may be combined into a single data store and/or that a single data store described herein may be separated into multiple data stores without departing from the scope of the present disclosure.

Autonomous vehicles 304 are configured to receive routes from route reservation system 302 and navigate autonomously along the routes. In some embodiments, autonomous vehicle 304 is an aircraft. In other embodiments, any other type of autonomous vehicle 304 capable of navigating along a route may be used, such as a wheeled vehicle. As shown, autonomous vehicle 304 includes a communication interface 316, one or more vehicle status sensor devices 318, a power supply 320, one or more processors 314, one or more propulsion devices 322, and a computer readable medium 324.

In some embodiments, communication interface 316 includes hardware and software to enable any suitable communication technology for communicating with route reservation system 302. In some embodiments, communication interface 316 includes a plurality of communication interfaces 316, each for an appropriate environment. For example, communication interface 316 may include a remote wireless interface, such as a 4G or LTE interface, or any other type of remote wireless interface (e.g., 2G, 3G, 5G, or WiMAX) for communicating with route reservation system 302 when traversing a route. Communication interface 316 may also include a mid-range wireless interface, such as a Wi-Fi interface, used when autonomous vehicle 304 is in an area near a starting location or end point where Wi-Fi coverage is made available to a provider of route reservation system 302. Communication interface 316 may also include a short range wireless interface, such as a bluetooth interface, that is used when autonomous vehicle 304 is in a maintenance position or stationary and waiting for a route to be allocated. Communication interface 316 may also include a wired interface, such as an ethernet interface or a USB interface, which may also be used when autonomous vehicle 304 is in a maintenance position or stationary and waiting for a route to be allocated.

In some embodiments, carrier state sensor device 318 is configured to detect the states of the various components of autonomous carrier 304 and send signals representative of these states to other components of autonomous carrier 304. Some non-limiting examples of the vehicle status sensor device 318 include a battery status sensor and a propulsion device health sensor.

In some embodiments, power source 320 may be any suitable device or system for storing and/or generating power. Some non-limiting examples of power source 320 include one or more batteries, one or more solar panels, a fuel tank, and combinations thereof. In some embodiments, propulsion device 322 may include any suitable device for causing autonomous vehicle 304 to travel along a route. For an aircraft, propulsion devices 322 may include devices such as, but not limited to, one or more motors, one or more propellers, and one or more flight control surfaces. For wheeled vehicles, propulsion devices 322 may include devices such as, but not limited to, one or more motors, one or more wheels, and one or more steering mechanisms. In some embodiments, processor 314 may comprise any type of computer processor capable of receiving signals from other components of autonomous carrier 304 and executing instructions stored on computer readable medium 324. In some embodiments, computer-readable medium 324 may include one or more devices capable of storing information for access by processor 314. In some embodiments, computer readable medium 324 may include one or more of a hard disk drive, a flash drive, an EEPROM, and combinations thereof.

As shown, the computer-readable medium 324 has stored thereon a route data storage 326, a route validation engine 328, and a route traversal engine 330. In some embodiments, route validation engine 328 is configured to analyze routes received from route reservation system 302 to determine whether autonomous vehicles 304 are able to traverse the route, including, but not limited to, determining whether sufficient power is available to complete the route, and determining whether performance capabilities are available for traversing the route. In some embodiments, route traversing engine 330 is configured to cause propulsion device 322 to propel autonomous vehicle 304 through a route received from route reservation system 302. The route-traversing engine 330 can use signals from other devices to assist in positioning and navigation, as is typical for autonomous vehicles 304, such as GPS sensor devices, vision-based navigation devices, accelerometers, LIDAR devices, and/or other devices not further shown or described herein.

Further details regarding the functionality of route reservation system 302 and autonomous vehicle 304 are provided below.

Fig. 4A-4B are flow diagrams illustrating non-limiting example embodiments of a method of optimizing a route of an autonomous vehicle according to aspects of the present disclosure. At block 402, route determination engine 306 of route reservation system 302 plans a path for autonomous vehicle 304. In some embodiments, the path may be planned to start from a starting location and pass through one or more waypoints before returning to the endpoint. In some embodiments, activity (such as delivery) for each waypoint may also be included in the path. In some embodiments, path planning may involve ordering waypoints for efficient straight-line travel between segments of a path. In some embodiments, a route-finding algorithm, such as the a-x, dijkstra (Dijkstra) algorithm, bellman-Ford (Bellman-Ford) algorithm, or other route-finding algorithm, may be used to plan a particular path between points.

In some embodiments, the end portion of the path may guide the vehicle to a waiting position where the vehicle will wait as long as possible before traveling to a default safety endpoint. For example, a path for an aircraft may include hovering in the wait area 204 until a predetermined amount of time has elapsed, the battery level reaches a low battery threshold level, or some other wait ending state has been detected. Upon detection of the wait ending condition, the aircraft will follow the remainder of the path (remain) to the landing zone. The landing zone may be managed by a group of operators, who are ready to remove the incoming aircraft to avoid collisions. In this way, the vehicle is given a safe route all the way to the destination even if the vehicle does not receive an updated path from the waiting area 204 to the intended destination as described below. Landing at the default safe destination should be rare, as this would occur if route reservation system 302 were unable to provide an updated route to the vehicle to the intended destination.

At block 404, the route determination engine 306 establishes a sequence of one or more timing space reservations associated with the path. To establish the sequence, the route determination engine 306 may decompose the path into segments that are expected to traverse within a given amount of time based on the capabilities of the vehicle. Starting at the first segment corresponding to the start position, the route determination engine 306 determines the following times: at this time, the space associated with the first segment of the path is not reserved by any other existing timing space reservation stored in reserved data storage 312. Once the time is found, the route determination engine 306 creates a timing space reservation for the time and space and then creates a subsequent timing space reservation for the next segment of the path. As described above, the duration of each timing space reservation in the sequence may be increased throughout the sequence in order to accommodate increased uncertainty regarding the position of the carriers traveling on the path. In some embodiments, the established timing space reservation may be changed if a collision is found later in the path. In some embodiments, when a sequence of timing space reservations is established, the path may be changed from the best path found at block 402 to avoid conflicting timing space reservations. Such detours may be marked in the sequence and may be removed if the conflict is resolved later (as discussed further below).

At block 406, the route determination engine 306 stores the sequence of one or more timing space reservations in the reservation data storage 312 of the route reservation system 302 to establish a reserved route. In some embodiments, once the sequence of timing space reservations is stored as a reservation route in reservation data storage 312, the timing space reservations exclude other overlapping timing space reservations. At block 408, the route determination engine sends the reserved route to autonomous vehicle 304 via communication interface 308 of route reservation system 302. Autonomous vehicles 304 receive the reserved route and use the reserved route as an instruction for travel, as shown in fig. 7A-7B and discussed further below.

At block 410, change detection engine 310 of route reservation system 302 detects a route change state. In some embodiments, the route change state is any state that may be detected by route reservation system 302 that indicates that the reserved route may or should be changed. One non-limiting example includes detecting that autonomous vehicle 304 has reached waiting area 204, is approaching waiting area 204, or is in close proximity to the end of its reserved route. In some embodiments, route reservation system 302 may detect that autonomous vehicle 304 has arrived based on position telemetry sent by autonomous vehicle 304 to route reservation system 302. In some embodiments, route reservation system 302 may detect that autonomous vehicle 304 has arrived based on a medium range network signal (such as a Wi-Fi signal) received by the medium range wireless network associated with waiting area 204 or other end of the reserved route from autonomous vehicle 304.

Another non-limiting example of a route change state is a suspension state. In some embodiments, autonomous vehicle 304 may be able to detect a problem that results in a situation where autonomous vehicle 304 may not be able to safely complete a previously reserved route. For example, autonomous vehicle 304 may detect a failure or performance degradation of propulsion device 322, may detect a failure of a sensor, may detect that the amount of available power from power source 320 has fallen below an acceptable level, may detect that the battery charge level has fallen below a safety threshold, may detect an un-navigable obstacle, or may detect any other condition that may prevent autonomous vehicle 304 from safely completing a reserved route. In some embodiments, autonomous vehicle 304 may wirelessly send a notification that it has detected an abort condition to route reservation system 302 along with telemetry information. In some embodiments, route reservation system 302 may determine that an abort condition exists based on telemetry information that does not include a notification. For example, route reservation system 302 may detect that the battery charge level has fallen below a safety threshold based on telemetry information that directly reports the battery charge level.

Yet another non-limiting example of a route change state is the detection of an emergency that does not exist when calculating a reserved route. For example, route reservation system 302 may receive a signal indicating that a certain amount of airspace has been declared a temporary no-fly zone due to a disaster, an infraction, an unplanned event, or some other emergency; or a signal indicating that the road is closed due to an accident or any other reason. In this case, route reservation system 302 may attempt to provide a new route to the vehicle that avoids the emergency area.

Another non-limiting example of a route change state is the need to remove a detour. As described above, the route determination engine 306 may record the detour in the best path. Such a record of detour may also record the reason for detour, thus allowing the opportunity to remove detour if the reason for detour is resolved. Fig. 5A-5C illustrate example embodiments of routes with detour and detour removal according to various aspects of the present disclosure. As shown in fig. 5A, a first route 504 extends from the top of the figure and runs vertically downward in the figure. Each vertical arrow represents a timing space reservation of the first route 504.

The route determination engine 306 then plans a second route 502 to extend from the left side of the graph and travel horizontally right through the graph. The first time interval reservation of the second route 502 does not have any conflict. The second timing space reservation of the second route 502 conflicts with the timing space reservation of the first route 504. If the first route 504 is established while the second route 502 is being planned, the route determination engine 306 may create a detour for the second route 502 to avoid conflicts. As shown, the optimal route is indicated by dashed arrow 506, while the detour route to avoid collisions is indicated by curved arrow 508. Without further variation, the first autonomous vehicle would travel vertically along the first route 504 and the second autonomous vehicle would travel horizontally along the second route 502, detouring along the curved path 508 to avoid the first route 504.

Fig. 5B shows a route change state in which the need for detour has been removed. As shown, the second route 502 is currently the same and still includes a detour 508. However, the first route 504 has been updated such that its second illustrated timing space reservation and its third illustrated timing space reservation no longer cause a conflict to the second route 502. This may occur for any reason including, but not limited to, changing the first route 502 in response to detecting a route change state. The change detection engine 310 may be configured to detect such a state that no detour is required. As will be discussed further below, fig. 5C illustrates example results of planning a new route in response to removing a need for detour. As shown, the best path 506 has been used for the new path and the detour 508 has been removed (but is still shown in dashed lines for discussion purposes only).

The arrows and curves shown in fig. 5A-5C are simplified examples for discussion purposes only. In some embodiments, the paths, routes, and detours determined by the route determination engine 306 may include safe margins rather than just lines, and may include paths through three-dimensional space rather than two-dimensional regions.

Returning to fig. 4A, at block 412, the route determination engine 306 plans a new path for the autonomous vehicle 304 based on the route change state. The new path takes into account the route change state when planning the new path. As a non-limiting example, if the route change state is a detection that the autonomous vehicle 304 has reached the waiting area 204 or is near the waiting area 204, the new path may proceed directly from the waiting area 204 (or current vehicle position) to the end point without further pausing in the waiting area 204. As another non-limiting example, if the route change state is an abort state, the new path may be advanced from the current vehicle position to a maintenance position or other safe drop zone, or may be advanced from the current vehicle position through a simplified path that may be completed despite the existence of the abort state. As yet another non-limiting example, if the route change state is to remove the need for a detour, the new path may return to the best path avoided by the detour (as shown in fig. 5C). Similar techniques may be used to plan the new path as used to plan the original path at block 402. The new path may be planned in such a way that it branches from the original path without any discontinuity in position or speed.

The method 400 proceeds to a continuation terminal ("terminal a"). The method proceeds from terminal a (fig. 4B) to block 416. At block 416, the route determination engine 306 establishes a new sequence of one or more timing space reservations associated with the new path, and at block 418, the route determination engine 306 stores the new sequence of one or more timing space reservations in the reservation data storage 312 to establish the new route. Similar to block 404, the route determination engine 306 may decompose the new path into segments that are expected to traverse within a given amount of time based on the capabilities of the vehicle, and may determine the following times from other timing space reservations stored in the reservation data store 312 prior to creating a timing space reservation for the segment: at this time, the space associated with each segment is free. In some embodiments, the duration of the separate timing space reservation of the new sequence may be shorter than the duration of the remaining timing space reservations of the reserved route, as the new sequence does not have to compensate for the accumulated uncertainty in arrival time from the earlier part of the reserved route. The reduced duration of the new sequence may make it easier to avoid collisions between the new sequence and other routes stored in reserved data storage 312. This is particularly useful for high traffic flow paths such as paths from public waiting areas 204 to end points within warehouse 202.

One complication that arises when establishing a new sequence of timing space reservations is that at least some of the new timing space reservations may overlap with existing timing space reservations. Fig. 6 illustrates an example of how a new sequence of timing space reservations conflicts with existing timing space reservations in accordance with aspects of the present disclosure. As shown, autonomous vehicle 602 is associated with a reserved route 604 and is currently traveling on reserved route 604. At some point, a route change state is detected and the route determination engine 306 plans a new path that involves turning left from the existing reserved route 604. The timing space reservation for the new route 606 overlaps with the reserved route 604 at least in the shaded overlap region 608, because for at least some portions of the new route 606, the autonomous vehicle 602 will be in space that is also part of the reserved route 604.

If the route determination engine 306 attempts to avoid all conflicts between timing space reservations, planning a new route 606 will not be possible due to the conflicts in the overlap region 608. Thus, in some embodiments, if a conflict is between timing space reservations of the same autonomous vehicle 602, the route determination engine 306 ignores the conflict between timing space reservations when planning a new route. Such a collision will not result in a reduced security, as the same autonomous vehicle 602 cannot collide with itself.

Another complication that may occur when a new sequence of timing space reservations is established may be that multiple autonomous vehicles experience a route change state simultaneously and may wait to travel via a common path simultaneously. For example, multiple autonomous vehicles may have arrived at the waiting area 204 near the destination at approximately the same time, and may all be waiting for the allocation of a new route to travel from the waiting area 204 to the destination. In such embodiments, the route determination engine 306 may prioritize the plurality of autonomous vehicles using any suitable technique. As a non-limiting example, route determination engine 306 may use telemetry information to determine the autonomous vehicle with the lowest battery state of charge and may provide a new route that is temporally earlier than new routes provided to other autonomous vehicles. As another non-limiting example, the route determination engine 306 may determine a desired capability at the endpoint, such as an autonomous vehicle having a particular cargo capacity, or an autonomous vehicle having a battery state of charge sufficient to serve a subsequent task with minimal recharging, and may prioritize the autonomous vehicles having the desired capability to have an earlier route than other autonomous vehicles.

At block 420, the route determination engine 306 sends the new route to the autonomous vehicle 304 via the communication interface 308. In some embodiments, the transmission to autonomous vehicles 304 may occur via a connectionless protocol. Due to uncertainties in transmission, and the potential lack of persistent network connectivity of autonomous vehicles operating outside of line of sight, route determination engine 306 is unable to determine that autonomous vehicle 304 received a new route. Further, in some embodiments, autonomous vehicles 304 may independently decide whether to accept or reject a new route. Thus, at this point, route determination engine 306 cannot determine whether autonomous vehicle 304 will travel along the new route or the original reserved route, so route determination engine 306 continues to store both the timing space reservation for the reserved route and the timing space reservation for the new route in reserved data storage 312. This ensures that autonomous vehicle 304 will travel through the reserved space regardless of which route it chooses to follow.

At block 422, the route determination engine 306 receives a confirmation of the new route from the autonomous vehicle 304 via the communication interface 308. The acknowledgement indicates that autonomous vehicle 304 has accepted the new route and will travel along the new route instead of the reserved route. In response to the acknowledgement, the route determination engine 306 deletes one or more timing space reservations associated with the reserved route from the reservation data storage 312 at block 424. In some embodiments, route determination engine 306 may alternatively receive a rejection of the new route from autonomous vehicle 304, indicating that autonomous vehicle 304 is to alternatively travel along the original reserved route. In this case, the route determination engine 306 may delete one or more timing space reservations associated with the new route from the reservation data store.

At block 702, autonomous vehicle 304 receives a reserved route via communication interface 316. In some embodiments, the reserved route includes both the route that autonomous vehicle 304 is to travel and at least the time that autonomous vehicle 304 should begin traversing the path. In some embodiments, the reservation route received by autonomous vehicle 304 may also include an indication of a timing space reservation such that autonomous vehicle 304 may time its travel to coincide with the timing space reservation throughout the reservation route. At block 704, autonomous vehicle 304 stores the reserved route in route data storage 326 of autonomous vehicle 304.

At block 706, route-traversing engine 330 of autonomous vehicle 304 actuates one or more propulsion devices 322 of autonomous vehicle 304 to traverse the reserved route by autonomous vehicle 304. For example, route traversing engine 330 can wait until a start time determined based on the reserved route and then activate one or more propellers or wheels of autonomous vehicle 304 to begin traversing the route. The route-traversing engine 330 may use signals from various devices to determine the position of the autonomous vehicle 304 and may use the position of the autonomous vehicle 304 to change control inputs to the propulsion devices 322 in order to traverse the route by the autonomous vehicle 304.

At block 708, autonomous vehicle 304 transmits telemetry information via communication interface 316. Telemetry information may be received by route reservation system 302. Telemetry information transmitted by autonomous vehicles 304 may include information including, but not limited to, air speed, ground speed, heading, bearing, altitude, location, and battery power. Telemetry information may allow change detection engine 310 to determine various route change states, such as removing the need for detours. Telemetry information may also allow change detection engine 310 (or another component of route reservation system 302) to check whether autonomous vehicle 304 is operating within an expected timing space reservation time associated with the reserved route. The route reservation system 302 may use this information to widen the existing headroom reservation time (if the autonomous vehicle 304 lags or leads the existing headroom reservation time) or narrow the existing headroom reservation time (if the autonomous vehicle 304 travels as expected and thus reduces the uncertainty for future headroom reservations). If autonomous vehicle 304 lags the existing timing space reservation time, route reservation system 302 may detect it as a route change state and may plan a new route based on the actual location of autonomous vehicle 304.

At optional block 710, the route-traversing engine 330 detects an abort condition based on information generated by one or more vehicle status sensor devices 318 of the autonomous vehicle 304, and at optional block 712, the route-traversing engine 330 sends an abort notification via the communication interface 316. As described above, the suspension condition may include a state that: wherein route-traversing engine 330 has determined based on this information that autonomous vehicles 304 will not be able to safely complete the reserved route. As a non-limiting example, route traversal engine 330 can determine that the battery charge level is too low to safely reach the end of the reserved route. As another non-limiting example, route-traversing engine 330 can determine that a component of autonomous vehicle 304, such as propulsion device 322, has failed and needs repair. Blocks 710 and 712 are shown as optional because route traversing engine 330 may not detect an abort condition before completing the reserved route (or at least returning to waiting area 204 or other area near the end of the reserved route).

At block 714, the autonomous vehicle 304 receives the new route via the communication interface 316. The received new route is a new route that the route determination engine 306 determines in response to detecting the route change state. The method 700 proceeds to a continuation terminal ("terminal B"). The method 700 proceeds from terminal B (fig. 7B) to block 716. At block 716, the route validation engine 328 of the autonomous vehicle 304 analyzes the new route to determine whether the new route is acceptable. In some embodiments, route validation engine 328 may analyze the new route by determining whether the battery state of charge is sufficient to safely complete the new route. In some embodiments, route validation engine 328 may analyze the new route by determining whether performance characteristics of autonomous vehicle 304 (including one or more of a turning radius, a maximum or minimum operating altitude, and a maximum or minimum operating speed) are sufficient to traverse the new route. In some embodiments, route validation engine 328 may analyze the new route to ensure that switching from the reserved route to the new route does not require any discontinuities in location or speed.

At decision block 718, a determination is made based on whether the new route is found to be acceptable. If the route is found to be acceptable, the result of decision block 718 is "yes" and method 700 proceeds to block 720. At block 720, the route validation engine 328 sends a validation of the new route via the communication interface 316. The acknowledgement indicates that autonomous vehicle 304 will begin traversing a new route instead of a reserved route. At block 722, the route validation engine 328 stores the new route in the route data storage 326 instead of reserving the route. In some embodiments, route validation engine 328 may delete the reserved route from route data store 326 because route traversal engine 330 no longer needs it. At block 724, the route traversing engine 330 actuates the one or more propulsion devices 322 to traverse the new route by the autonomous vehicle 304.

Returning to decision block 718, if the route is found to be unacceptable, the result of decision block 718 is no and method 700 proceeds to optional block 726. At optional block 726, route validation engine 328 sends a rejection of the new route via communication interface 316. The rejection indicates that autonomous vehicle 304 will continue along the reserved route instead of the new route. Block 726 is shown as optional because if no acknowledgement is received, route reservation system 302 may assume that the new route was rejected, and thus the transmission of the rejection may not be necessary for secure operation. Transmission refusal may allow route reservation system 302 to operate more efficiently because there will be fewer unused timing space reservations in reservation data storage 312. At block 728, route traversing engine 330 continues to actuate one or more propulsion devices 322 to traverse the reserved route by autonomous vehicles 304.

While illustrative embodiments have been illustrated and described, it will be appreciated that various changes can be made therein without departing from the spirit and scope of the invention.

Claims

1. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, in response to execution by one or more processors of one or more computing devices, cause the computing devices to perform actions for updating a reserved route for an autonomous vehicle, wherein the reserved route comprises a sequence of one or more timing space reservations, the actions comprising:

planning a new route to replace the reserved route;

transmitting the new route to the autonomous vehicle; and

the one or more timing space reservations are deleted in response to receiving an acknowledgement from the autonomous vehicle that the new route is accepted.

2. The computer-readable medium of claim 1, wherein the autonomous vehicle is an aircraft.

3. The computer-readable medium of claim 1, wherein the actions further comprise detecting a route change state that triggers planning of a new route.

4. A computer readable medium according to claim 3, wherein the reserved route comprises one or more detour segments around at least one conflicting timing space reservation, and wherein detecting a route change state triggering planning of a new route comprises detecting that at least one conflicting timing space reservation has been deleted.

5. The computer readable medium of claim 3, wherein detecting a route change state that triggers planning of a new route comprises detecting a fault state on an autonomous vehicle.

6. A computer readable medium as in claim 3, wherein the reserved route comprises a timing space reservation for a waiting location near an end of the reserved route, and wherein detecting a route change state that triggers planning of a new route comprises detecting that an autonomous vehicle has reached the waiting location.

7. The computer-readable medium of claim 6, wherein the autonomous vehicle is an aircraft, wherein the waiting location is a hover location, and wherein planning a new route to replace a reserved route comprises establishing a sequence of timing space reservations from hover location to endpoint.

8. The computer-readable medium of claim 7, wherein the terminus is within a building, and wherein establishing a sequence of timing space reservations from a hover position to the terminus comprises establishing a sequence of timing space reservations through an opening in the building to reach the terminus.

9. The computer-readable medium of claim 1, wherein planning a new route to replace a reserved route comprises:

Determining a path from the current location to the destination via one or more waypoints;

determining a time reserved for a timing space where no collision exists for the path; and

one or more timing space reservations are added to the new route for segments of the path.

10. The computer-readable medium of claim 9, wherein determining a time for which there is no conflicting timing space reservation for a path comprises: the conflicting timing space reservations associated with the autonomous vehicle are ignored.

11. The computer-readable medium of claim 9, wherein determining a time for which there is no conflicting timing space reservation for a path comprises: the plurality of autonomous vehicles having conflicting paths are prioritized.

12. The computer-readable medium of claim 11, wherein prioritizing a plurality of autonomous vehicles having conflicting paths comprises: the plurality of autonomous vehicles having conflicting paths are prioritized based on battery status of the plurality of autonomous vehicles.

13. The computer-readable medium of claim 12, wherein prioritizing the plurality of autonomous vehicles having conflicting paths based on battery status comprises: the earliest timing space reservation is provided to the autonomous vehicle with the lowest battery state of charge.

14. The computer-readable medium of claim 12, wherein prioritizing the plurality of autonomous vehicles having conflicting paths based on battery status comprises: the earliest timing space reservation is provided to autonomous vehicles with battery states of charge matching the requirements of the pending tasks.

15. The computer-readable medium of claim 11, wherein prioritizing a plurality of autonomous vehicles having conflicting paths comprises: the plurality of autonomous vehicles having conflicting paths are prioritized based on whether the autonomous vehicles include features required for pending tasks.

16. An autonomous vehicle, comprising:

a communication interface;

one or more propulsion devices;

one or more processors; and

a computer-readable medium having stored thereon computer-executable instructions that, in response to execution by the one or more processors, cause an autonomous vehicle to perform actions comprising:

operating one or more propulsion devices to traverse a reservation route by an autonomous vehicle, wherein the reservation route comprises a sequence of one or more timing space reservations; and

when traversing a reserved route:

receiving the updated route via the communication interface;

Analyzing the updated route to determine whether the updated route is acceptable; and

in response to determining that the updated route is acceptable:

transmitting an acknowledgement of the updated route via the communication interface to cause the controller to delete one or more timing space reservations of the reserved space; and

the propulsion device is operated to cause the autonomous vehicle to traverse the updated route instead of the reserved route.

17. The autonomous vehicle of claim 16, wherein the autonomous vehicle is an aircraft, and wherein the propulsion device comprises at least one of a propeller and a flight control surface.

18. The autonomous vehicle of claim 16, further comprising one or more vehicle state sensor devices, and wherein the acts further comprise:

detecting an abort condition based on information generated by the one or more vehicle state sensor devices; and

the abort notification is sent via the communication interface.

19. The autonomous vehicle of claim 16, wherein analyzing the updated route to determine whether the updated route is acceptable comprises:

determining a predicted power usage for completing the updated route; and

the predicted power usage is compared to the battery state of charge.

20. The autonomous vehicle of claim 16, wherein analyzing the updated route to determine whether the updated route is acceptable comprises:

determining one or more vehicle performance characteristics for completing the updated route; and

the one or more vehicle performance characteristics are compared to performance characteristics of an autonomous vehicle.